2,842 skills found ¡ Page 73 of 95
nWave-ai / nw-data-architecture-patternsData architecture patterns (warehouse, lake, lakehouse, mesh), ETL/ELT pipelines, streaming architectures, scaling strategies, and schema design patterns
nWave-ai / nw-discovery-workflow4-phase discovery workflow with decision gates, phase transitions, success metrics, and state tracking
nWave-ai / nw-research-methodologyResearch output templates, distillation workflow, and quality standards for evidence-driven research
nWave-ai / nw-review-workflowDetailed review process, v2 validation checklist, and scoring methodology for agent definition reviews
Agentfy-io / Agentfyđ¤ Agentfy is a modular microservices architecture designed to process user requests and execute workflows across multiple social media platforms. ASK ONCE, LET THE AGENT DO THE REST!
anombyte93 / generatePhase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholders_found, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native comâĻ
anombyte93 / handoffPhase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.mdâĻ
anombyte93 / customise-workflowCustomise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json.
anombyte93 / setupPhase 0 of the prd-taskmaster pipeline. Resolves the active backend, initializes the project, configures the provider stack when the TaskMaster backend is active (DETECT-FIRST â never overwrite a working user config), and verifies the AI pipeline.
anombyte93 / discoverPhase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present.
aannoo / hcomLet AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi
Enderfga / claw-orchestratorRun Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.
openai / tunnel-clientCustomer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.
rokpiy / auto-commenterA Claude skill that automatically posts personalized, authentic comments in your target communities.
shobcoder / shobShob â an AI agent that delivers high-quality coding & automation work
devopness / devopnessDevopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.
oliver-kriska / claude-elixir-phoenixClaude Code plugin for Elixir/Phoenix/LiveView â 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.
levnikolaevich / ln-43-code-modernizerModernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.
Hainrixz / the-architectA Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context â EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield.
oliver-kriska / fullDeliver a large, cross-domain Phoenix feature or complete end-to-end system through planning, implementation, verification, and review
oliver-kriska / pr-reviewAddress feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments
oliver-kriska / obanUse when writing, scheduling, testing or debugging Oban jobs, even for a how-to question: workers, cron, retries, unique jobs, queues, Pro Workflow/Batch. Load it before touching job code; it holds the job rules.
oliver-kriska / plugin-dev-workflowGuide plugin development workflow â editing skills, agents, hooks, or eval framework in this repo
oliver-kriska / deployElixir/Phoenix deployment patterns â Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays
oliver-kriska / intent-detectionRoute ambiguous or mixed Phoenix/LiveView/Ecto requests before choosing a workflow
oliver-kriska / permissionsRecommend safe Bash permissions for Elixir mix commands in settings.json
oliver-kriska / phx-permissionsRecommend safe Bash permissions for Elixir mix commands in settings.json.
michael-denyer / automate-meUse for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works.
RandallLiuXin / GodotMakerAutonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode
RandallLiuXin / gm-rescueSelf-diagnostic skill for godotmaker itself. Invoked when the main pipeline can't make progress (e.g. several fixgap rounds in a row failed to converge)
